Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4914 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.3537. Min Act: -0.0000

Data Index: 1220129 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.4494. Min Act: -0.0000

Data Index: 27896 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.2900. Min Act: -0.0000

Data Index: 1179623 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.2225. Min Act: -0.0000

Data Index: 337419 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.1011. Min Act: -0.0000

Data Index: 625116 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.0948. Min Act: -0.0000

Data Index: 37560 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.1220. Min Act: -0.0000

Data Index: 196360 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1188675 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.0778. Min Act: -0.0000

Data Index: 737551 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.0579. Min Act: -0.0000

Data Index: 806759 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.0529. Min Act: -0.0000

Data Index: 647520 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.0172. Min Act: -0.0000

Data Index: 901721 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1332570 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.9812. Min Act: -0.0000

Data Index: 472556 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.9853. Min Act: -0.0000

Data Index: 141578 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.9704. Min Act: -0.0000

Data Index: 99216 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.0315. Min Act: -0.0000

Data Index: 43109 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.0404. Min Act: -0.0000

Data Index: 565367 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1307522 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 1.4494. Min Range: -1.4494

Max Act: 0.8959. Min Act: -0.0000

Data Index: 206041 (C4 (Web Text))

Max Activating Token Index: 856